Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Port-environment-oriented man-machine hybrid automatic driving test method and test platform thereof

A technology for autonomous driving and testing methods, applied in the testing of machine/structural components, vehicle testing, measuring devices, etc. The effect of testing efficiency, reducing testing cost and improving driving safety

Active Publication Date: 2020-04-14
CHANGJIAFENGXING SUZHOU INTELLIGENT TECH CO LTD
View PDF10 Cites 13 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, in recent years, Tesla, Google, Uber and other companies have caused a series of traffic accidents due to the instability and insufficient testing of their self-driving vehicle systems, which has caused people to panic about self-driving vehicles.

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Port-environment-oriented man-machine hybrid automatic driving test method and test platform thereof
  • Port-environment-oriented man-machine hybrid automatic driving test method and test platform thereof

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0043] Such as figure 1 As shown, the test method of the man-machine mixed driving automatic driving facing the port environment of the present invention comprises the following steps:

[0044] A. Virtual testing:

[0045] (1) Create a virtual vehicle driving environment based on SCANeR (simulating the vehicle driving environment in a port scene) based on the information collected from real weather conditions, road environments, and traffic scenarios and test requirements, and model according to the vehicle parameters of real vehicles or test requirements Create a vehicle model that conforms to the dynamics, and combine the geometric model of the perceived target in the driving environment of the vehicle with the physical model of the sensor itself for hybrid modeling to simulate its own on-board sensing system;

[0046](2) The vehicle model runs in the virtual vehicle driving environment in the step (1), and detects whether the vehicle model can perceive the road environment...

Embodiment 2

[0058] On the basis of Embodiment 1, after each test is completed, the test data of the virtual vehicle driving environment, the closed field test and the actual field test are saved, so as to facilitate the creation of the scene database in the later stage to ensure the scene of the automatic driving vehicle test Rich types.

[0059] Furthermore, the scene database includes scene data adapted to various vehicle driving environments facing the port environment, closed field tests and actual port field tests.

[0060] Before each test, the saved test data is extracted from the created scene database for use or for later test comparative analysis.

Embodiment 3

[0062] The human-machine mixed driving automatic driving virtual test platform based on the test method described in Embodiment 1 of the present invention includes a vehicle driving environment generation subsystem, a vehicle dynamics model subsystem, a virtual sensor simulation subsystem, a measurement and control subsystem, a test The result analysis and evaluation subsystem and the driving simulator, the communication connection between the vehicle driving environment generation subsystem, the vehicle dynamics model subsystem, the virtual sensor simulation subsystem, the measurement and control subsystem, the test result analysis and evaluation subsystem and the driving simulator ;

[0063] The vehicle driving environment generating subsystem is used to create a virtual vehicle driving environment according to the information collected in natural scenes or the information of test requirements; the vehicle driving environment generating subsystem includes a road scene generat...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention discloses a port-environment-oriented man-machine hybrid automatic driving test method and a test platform thereof. On the basis of SCANeR, a vehicle driving environment required by a test is created; a vehicle model is established according to vehicle parameters, the detection of a simulation sensor is far away from a virtual vehicle-mounted sensor system, and whether the vehicle model can sense the road environment, plan a driving route automatically, and control the vehicle to reach a predetermined target through the vehicle-mounted sensor system of the vehicle model is detected in a virtual vehicle driving environment, and the boundary of the automatic driving function is verified. The vehicle model and the vehicle-mounted sensing system are virtualized, and virtual testing is firstly carried out; in a virtual test, real-time man-machine switching driving modes can be realized through a driving simulator, so that the vehicle driving safety is improved. Moreover, automatic driving trajectory planning, trajectory tracking and execution controller performance of the vehicle model under different traffic scenes can be virtualized according to test requirements in thevirtual test, so that the test cost is effectively reduced, and test efficiency is improved.

Description

technical field [0001] The invention belongs to the technical field of unmanned driving testing, and in particular relates to a testing method and a testing platform for human-machine mixed driving and automatic driving facing a port environment. Background technique [0002] With the rapid development of self-driving vehicles, our travel will become more efficient and more environmentally friendly. It can not only make up for the lack of human sensory ability, eliminate traffic accidents caused by human factors, reduce the intensity of human driving operations, but also control and predict According to the behavior and running status of the car, a reasonable travel route is planned according to the real-time road condition information. However, in recent years, companies such as Tesla, Google, and Uber have caused a series of traffic accidents due to unstable self-driving vehicle systems and insufficient testing, which has caused people to panic about self-driving vehicles....

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
IPC IPC(8): G01M17/007G06T19/00
CPCG01M17/007G06T19/006
Inventor 张祖锋刘凯胡阳
Owner CHANGJIAFENGXING SUZHOU INTELLIGENT TECH CO LTD
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com